A meaningful search engine using latent dirichlet allocation

• Main Author: Lim, Zhi Jun
• Format: Final Year Project Report
• Language: English
• Published: Universiti Malaysia Sarawak, (UNIMAS) 2014
• Subjects: QA75 Electronic computers. Computer science; QA76 Computer software; T Technology (General)
• Online Access: http://ir.unimas.my/id/eprint/39344/1/Lim%20Zhi%20ft.pdf; http://ir.unimas.my/id/eprint/39344/
• Institution: Universiti Malaysia Sarawak

This final year project is a research on a meaningful search engine using Latent Dirichlet Allocation (LDA). Our main concern is on the search engine algorithm to produce a better search result. Before we start, we are doing some study on the concepts of vector space model and LDA. The vector space model is based on the keyword searching method, but it is limited. It is harder to find out the related topic with the keyword for sometime. We believe that we can retrieve the searched documents by using the topic that related to it which is known as a semantic search model. Therefore, we aim to compare both searching methods as mentioned above which are vector space model and LDA. We have to evaluate and compare which searching method gives better and more accurate results. Hence, we are using LDA which derived from the semantic search model and believe it can give us more accurate and better results. Finally, we believe this is a significant contribution to the information retrieval field.